โ[ CVPR 2025 ] We introduce LT3SD, a novel latent 3D scene diffusion approach enabling high-fidelity generation of infinite 3D environments in a patch-by-patch and coarse-to-fine fashion.โ
โSeen2Scene takes an incomplete real-world 3D scan and generates a complete, coherent 3D scene using visibility-guided flow matching โ trained directly on real-world data.โ
